#形式化验证

共 9 篇带此标签

9 articles Newest 2026-11-21
Archive · #形式化验证 8 articles
Case Studies

Inside OpenAI’s Chip Design Agent Workflow

OpenAI has outlined how models can support chip design within a constrained engineering loop. The key is not RTL generation alone, but integrating models with EDA verification, deterministic controls, and human review.

2026-11-20 Source 2026-11-18 10 min 44 views
Case Studies

Claude Claims Two Black Hole Breakthroughs

Anthropic says Claude produced solutions to two open problems in black hole physics. The article separates the evidence into source, reproducibility, and peer-review tiers, then outlines a practical validation workflow for AI research teams.

2026-11-20 Source 2026-11-19 9 min 44 views
Opinion

Claude Code Verification: Less Code, More Evidence

Anthropic’s engineering team explains how it integrates automated tests, static analysis, and human judgment into the AI coding workflow, with practical guidance for building a CI verification gate.

2026-11-18 Source 2026-11-17 8 min 44 views
Case Studies

AI Agent Makes Gödel’s Theorems Searchable

AI is helping transcribe, index, and formally organize hundreds of proven theorems in Kurt Gödel’s unpublished manuscripts. Its practical value lies not in autonomous mathematical discovery, but in turning difficult archival material into a searchable and verifiable research resource.

2026-11-14 Source 2026-11-13 6 min 44 views
LLMs

Anthropic’s Path to Verifiable LLM Reasoning

Anthropic is exploring how formal guarantees could make LLM reasoning more reliable. The research offers a practical framework for verification, refusal, and human handoff in Agent deployments.

2026-11-05 Source 2026-11-04 8 min 44 views
Opinion

Terence Tao on Egoless Mathematics and AI Agents

As AI agents become active participants in mathematical research, credibility may shift from personal reputation to verifiable evidence. Tao's argument raises hard questions about validation, attribution, accountability, and whether removing author prestige merely creates new forms of authority.

2026-11-03 Source 2026-11-02 7 min 44 views
Case Studies

Can Qwen3.5 Really Design a RISC-V CPU?

Qwenputer uses Qwen3.5 to build an executable, deterministic RISC-V CPU. The project offers a useful test of AI-assisted hardware engineering, while also revealing the limits of its current verification.

2026-10-29 Source 2026-10-29 5 min 44 views
LLMs

Can LLMs Make Formal Verification Practical?

Anthropic is exploring LLMs for formal software verification, where machine-checkable proofs offer stronger guarantees than passing tests. The approach could reduce manual trial and error, but specification quality, proof planning, and verification costs remain major barriers.

2026-10-23 Source 2026-10-22 6 min 44 views